Trip Prediction Using GIS for Vehicle Energy Efficiency. Karbowski, D., Rousseau, A., Smis-Michel, V., & Vermeulen, V. In ITS World Congress, Detroit, USA, September, 2014. ![Trip Prediction Using GIS for Vehicle Energy Efficiency [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex In this paper, we present a novel trip prediction process whose main applications include vehicle energy efficiency optimization. The process is composed of multiple parts. First, a Markov chain model is built from quality-checked, real-world vehicle speed data. Secondly, a geographical information system (GIS), ADAS-RP, is used to define a real-world itinerary on a map-based interface. Finally, an algorithm runs the Markov chains under constraints from the GIS. As a result, any number of second-by-second stochastic speed profiles can be generated for a given itinerary. These speed profiles can then be inputs to vehicle powertrain models such as Autonomie, which can be used to predict energy consumption and other operational parameters. An example of the application of speed prediction is also described, involving route-based energy management for plug-in hybrid electric vehicles, in which the knowledge of future speed profiles can be used to find the optimal energy split.
@inproceedings{karbowski_trip_2014,
address = {Detroit, USA},
title = {Trip {Prediction} {Using} {GIS} for {Vehicle} {Energy} {Efficiency}},
url = {https://anl.box.com/s/lj4108w9nd5r01zocyb3deqon0v59tli},
abstract = {In this paper, we present a novel trip prediction process whose main applications include vehicle energy efficiency optimization. The process is composed of multiple parts. First, a Markov chain model is built from quality-checked, real-world vehicle speed data. Secondly, a geographical information system (GIS), ADAS-RP, is used to define a real-world itinerary on a map-based interface. Finally, an algorithm runs the Markov chains under constraints from the GIS. As a result, any number of second-by-second stochastic speed profiles can be generated for a given itinerary. These speed profiles can then be inputs to vehicle powertrain models such as Autonomie, which can be used to predict energy consumption and other operational parameters. An example of the application of speed prediction is also described, involving route-based energy management for plug-in hybrid electric vehicles, in which the knowledge of future speed profiles can be used to find the optimal energy split.},
booktitle = {{ITS} {World} {Congress}},
author = {Karbowski, Dominik and Rousseau, Aymeric and Smis-Michel, Vivien and Vermeulen, Valentin},
month = sep,
year = {2014},
keywords = {Driver Modeling, SVTRIP},
}
Downloads: 0
{"_id":"caBpWoRredoh8nEMs","bibbaseid":"karbowski-rousseau-smismichel-vermeulen-trippredictionusinggisforvehicleenergyefficiency-2014","authorIDs":[],"author_short":["Karbowski, D.","Rousseau, A.","Smis-Michel, V.","Vermeulen, V."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Detroit, USA","title":"Trip Prediction Using GIS for Vehicle Energy Efficiency","url":"https://anl.box.com/s/lj4108w9nd5r01zocyb3deqon0v59tli","abstract":"In this paper, we present a novel trip prediction process whose main applications include vehicle energy efficiency optimization. The process is composed of multiple parts. First, a Markov chain model is built from quality-checked, real-world vehicle speed data. Secondly, a geographical information system (GIS), ADAS-RP, is used to define a real-world itinerary on a map-based interface. Finally, an algorithm runs the Markov chains under constraints from the GIS. As a result, any number of second-by-second stochastic speed profiles can be generated for a given itinerary. These speed profiles can then be inputs to vehicle powertrain models such as Autonomie, which can be used to predict energy consumption and other operational parameters. An example of the application of speed prediction is also described, involving route-based energy management for plug-in hybrid electric vehicles, in which the knowledge of future speed profiles can be used to find the optimal energy split.","booktitle":"ITS World Congress","author":[{"propositions":[],"lastnames":["Karbowski"],"firstnames":["Dominik"],"suffixes":[]},{"propositions":[],"lastnames":["Rousseau"],"firstnames":["Aymeric"],"suffixes":[]},{"propositions":[],"lastnames":["Smis-Michel"],"firstnames":["Vivien"],"suffixes":[]},{"propositions":[],"lastnames":["Vermeulen"],"firstnames":["Valentin"],"suffixes":[]}],"month":"September","year":"2014","keywords":"Driver Modeling, SVTRIP","bibtex":"@inproceedings{karbowski_trip_2014,\n\taddress = {Detroit, USA},\n\ttitle = {Trip {Prediction} {Using} {GIS} for {Vehicle} {Energy} {Efficiency}},\n\turl = {https://anl.box.com/s/lj4108w9nd5r01zocyb3deqon0v59tli},\n\tabstract = {In this paper, we present a novel trip prediction process whose main applications include vehicle energy efficiency optimization. The process is composed of multiple parts. First, a Markov chain model is built from quality-checked, real-world vehicle speed data. Secondly, a geographical information system (GIS), ADAS-RP, is used to define a real-world itinerary on a map-based interface. Finally, an algorithm runs the Markov chains under constraints from the GIS. As a result, any number of second-by-second stochastic speed profiles can be generated for a given itinerary. These speed profiles can then be inputs to vehicle powertrain models such as Autonomie, which can be used to predict energy consumption and other operational parameters. An example of the application of speed prediction is also described, involving route-based energy management for plug-in hybrid electric vehicles, in which the knowledge of future speed profiles can be used to find the optimal energy split.},\n\tbooktitle = {{ITS} {World} {Congress}},\n\tauthor = {Karbowski, Dominik and Rousseau, Aymeric and Smis-Michel, Vivien and Vermeulen, Valentin},\n\tmonth = sep,\n\tyear = {2014},\n\tkeywords = {Driver Modeling, SVTRIP},\n}\n\n","author_short":["Karbowski, D.","Rousseau, A.","Smis-Michel, V.","Vermeulen, V."],"key":"karbowski_trip_2014","id":"karbowski_trip_2014","bibbaseid":"karbowski-rousseau-smismichel-vermeulen-trippredictionusinggisforvehicleenergyefficiency-2014","role":"author","urls":{"Paper":"https://anl.box.com/s/lj4108w9nd5r01zocyb3deqon0v59tli"},"keyword":["Driver Modeling","SVTRIP"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://vms.es.anl.gov/publications/bibtex","creationDate":"2019-06-07T18:27:12.679Z","downloads":0,"keywords":["driver modeling","svtrip"],"search_terms":["trip","prediction","using","gis","vehicle","energy","efficiency","karbowski","rousseau","smis-michel","vermeulen"],"title":"Trip Prediction Using GIS for Vehicle Energy Efficiency","year":2014,"dataSources":["WZSd6SdWp6wSKRgj6","zbKe4TQXjm3puEXsu"]}